{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TLSPOJXGQ5KLPW3XMQVO6XUEQB","short_pith_number":"pith:TLSPOJXG","schema_version":"1.0","canonical_sha256":"9ae4f726e68754b7db77642aef5e848041d2464d62da0b9f4b23590d7f3bdc09","source":{"kind":"arxiv","id":"2011.11765","version":2},"attestation_state":"computed","paper":{"title":"Boosting Contrastive Self-Supervised Learning with False Negative Cancellation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Maryam Khademi, Matthew R. Walter, Michael Maire, Simon Kornblith, Tri Huynh","submitted_at":"2020-11-23T22:17:21Z","abstract_excerpt":"Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While positive pairs can be generated reliably (e.g., as different views of the same image), it is difficult to accurately establish negative pairs, defined as samples from different images regardless of their semantic content or visual features. A fundamental problem in contrastive learning is mitigating the effects of false negatives. Contrasting false negatives induc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.11765","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-23T22:17:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"61fb653ef279c5eacfe96a2954e3cf1b4d0987f2b4a51ff67e284ff441755da9","abstract_canon_sha256":"cd6de5f83995a9895515f10ba7f27acf9395539a86a1c5e6bc3dbe1233f4c085"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:51.018190Z","signature_b64":"ELgPJ8yFLCbcW5AJ1CZeDpfbrSwbgjwi2EtCBpFmhuV3jNmVBsqYQ69NyogTwcrDzKdea3a7x1w8T/64b1laBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ae4f726e68754b7db77642aef5e848041d2464d62da0b9f4b23590d7f3bdc09","last_reissued_at":"2026-07-05T03:44:51.017822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:51.017822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Contrastive Self-Supervised Learning with False Negative Cancellation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Maryam Khademi, Matthew R. Walter, Michael Maire, Simon Kornblith, Tri Huynh","submitted_at":"2020-11-23T22:17:21Z","abstract_excerpt":"Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While positive pairs can be generated reliably (e.g., as different views of the same image), it is difficult to accurately establish negative pairs, defined as samples from different images regardless of their semantic content or visual features. A fundamental problem in contrastive learning is mitigating the effects of false negatives. Contrasting false negatives induc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11765","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.11765/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.11765","created_at":"2026-07-05T03:44:51.017878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.11765v2","created_at":"2026-07-05T03:44:51.017878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11765","created_at":"2026-07-05T03:44:51.017878+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLSPOJXGQ5KL","created_at":"2026-07-05T03:44:51.017878+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLSPOJXGQ5KLPW3X","created_at":"2026-07-05T03:44:51.017878+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLSPOJXG","created_at":"2026-07-05T03:44:51.017878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18852","citing_title":"Aligning Implied Statements for Implicit Hate Speech Generalizability with Context-Bounded Semi-hard Negative Mining","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB","json":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB.json","graph_json":"https://pith.science/api/pith-number/TLSPOJXGQ5KLPW3XMQVO6XUEQB/graph.json","events_json":"https://pith.science/api/pith-number/TLSPOJXGQ5KLPW3XMQVO6XUEQB/events.json","paper":"https://pith.science/paper/TLSPOJXG"},"agent_actions":{"view_html":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB","download_json":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB.json","view_paper":"https://pith.science/paper/TLSPOJXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.11765&json=true","fetch_graph":"https://pith.science/api/pith-number/TLSPOJXGQ5KLPW3XMQVO6XUEQB/graph.json","fetch_events":"https://pith.science/api/pith-number/TLSPOJXGQ5KLPW3XMQVO6XUEQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB/action/storage_attestation","attest_author":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB/action/author_attestation","sign_citation":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB/action/citation_signature","submit_replication":"https://pith.science/pith/TLSPOJXGQ5KLPW3XMQVO6XUEQB/action/replication_record"}},"created_at":"2026-07-05T03:44:51.017878+00:00","updated_at":"2026-07-05T03:44:51.017878+00:00"}